Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover safety (readOnlyHint=true, destructiveHint=false), and the description adds value beyond them by disclosing the shape of part of the payload (the `system` object with `default: {id,title,url} | null` plus `available`). It stops short of describing what is returned for the remaining types (docs, design-system, whiteboard, tldraw) or what happens on an invalid type, so it is strong but not exhaustive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, both front-loaded: the first defines the resource and the value space, the second gives the calling-order rule. The parenthetical type list and conditional return detail are dense but every clause is load-bearing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does explain the conditional `system` payload, which is the piece an agent could otherwise misread, and the workflow ordering is covered. The remaining gap is return-shape coverage for the non-design types and error behavior, which is minor for a read-only lookup tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the schema declares `type` as a bare string with no enum, so the description carries the full burden — and it does, enumerating all eight accepted values (html, docs, slides, dashboard, design, design-system, whiteboard, tldraw verbatim). Without this enumeration an agent would have no way to know valid inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Return the authoring guide (SKILL.md)') and enumerates the artifact types it applies to. It is clearly distinguishable from siblings like get_artifact (fetch an existing artifact) and systems_list, since it returns authoring guidance rather than content.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly prescribes ordering — 'Call get_skill first, before publish_html, create_artifact or write_files' — naming the exact downstream tools and the reason ('so you use the documented tools correctly'). It also explains when the returned `system` field matters ('or whether to ask the user'), removing ambiguity for the design-related types.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.